Tomé Marie-Hélène, Gjini Megi, Zhu Shaoyu, Kabarriti Rafi, Guha Chandan, Garg Madhur K, Tomé Wolfgang A, Brodin N Patrik
Institute for Onco-Physics, Albert Einstein College of Medicine, Bronx, USA.
Radiation Oncology, Montefiore Medical Center and Albert Einstein College of Medicine, Bronx, USA.
Cureus. 2021 Aug 25;13(8):e17432. doi: 10.7759/cureus.17432. eCollection 2021 Aug.
Objectives This study aimed to evaluate quantitative and qualitative screening measures for anomalous computed tomography (CT) scans in cancer patients with potential coronavirus disease 2019 (COVID-19) as an automated detection tool in a radiation oncology treatment setting. Methods We identified a non-COVID-19 cohort and patients with suspected COVID-19 with chest CT scans from February 1, 2020 to June 30, 2020. Lungs were segmented, and a mean normal Hounsfield Unit (HU) histogram was generated for the non-COVID-19 CT scans; these were used to define thresholds for designating the COVID-19-suspected histograms as normal or abnormal. Statistical measures were computed and compared to the threshold levels, and density maps were generated to examine the difference between lungs with and without COVID-19 qualitatively. Results The non-COVID-19 cohort consisted of 70 patients with 70 CT scans, and the cohort of suspected COVID-19 patients consisted of 59 patients with 80 CT scans. Sixty-two patients were positive for COVID-19. The mean HUs and skewness of the intensity histogram discriminated between COVID-19 positive and negative cases, with an area under the curve of 0.948 for positive and 0.944 for negative cases. Skewness correctly identified 57 of 62 positive cases, whereas mean HUs correctly identified 17 of 18 negative cases. Density maps allowed for visualization of the temporal evolution of COVID-19 disease. Conclusions The statistical measures and density maps evaluated here could be employed in an automated screening algorithm for COVID-19 infection. The accuracy is high enough for a simple and rapid screening tool for early identification of suspected infection in patients treated with chemotherapy and radiation therapy already receiving CT scans as part of clinical care. This screening tool could also identify other infections that present critical risks for patients undergoing chemotherapy and radiation therapy, such as pneumonitis.
目的 本研究旨在评估针对疑似2019冠状病毒病（COVID-19）的癌症患者的计算机断层扫描（CT）异常扫描的定量和定性筛查措施，作为放射肿瘤治疗环境中的一种自动检测工具。方法 我们确定了一个非COVID-19队列以及2020年2月1日至2020年6月30日期间进行胸部CT扫描的疑似COVID-19患者。对肺部进行分割，并为非COVID-19 CT扫描生成平均正常亨斯菲尔德单位（HU）直方图；这些用于定义将疑似COVID-19直方图指定为正常或异常的阈值。计算统计量并与阈值水平进行比较，并生成密度图以定性检查有无COVID-19的肺部之间的差异。结果 非COVID-19队列包括70例患者的70次CT扫描，疑似COVID-19患者队列包括59例患者的80次CT扫描。62例患者COVID-19呈阳性。强度直方图的平均HU值和偏度区分了COVID-19阳性和阴性病例，阳性病例的曲线下面积为0.948，阴性病例为0.944。偏度正确识别了62例阳性病例中的57例，而平均HU值正确识别了18例阴性病例中的17例。密度图允许可视化COVID-19疾病的时间演变。结论 此处评估的统计量和密度图可用于COVID-19感染的自动筛查算法。对于作为临床护理一部分已经接受CT扫描的化疗和放疗患者，该准确性足以作为一种简单快速的筛查工具用于早期识别疑似感染。这种筛查工具还可以识别出对接受化疗和放疗的患者存在重大风险的其他感染，如肺炎。
